Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5564 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3666. Min Range: -6.3666
Max Act: 6.3666. Min Act: -0.1700
Data Index: 5895079 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3666. Min Range: -6.3666
Max Act: 6.0228. Min Act: -0.1700
Data Index: 5110978 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.9916. Min Act: -0.1700
Data Index: 1190498 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.8666. Min Act: -0.1700
Data Index: 1396147 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.8353. Min Act: -0.1700
Data Index: 3478499 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.8353. Min Act: -0.1700
Data Index: 3958337 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.8041. Min Act: -0.1700
Data Index: 4672125 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.8041. Min Act: -0.1700
Data Index: 2576308 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.7416. Min Act: -0.1700
Data Index: 816224 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.7416. Min Act: -0.1700
Data Index: 2333330 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.7103. Min Act: -0.1700
Data Index: 1066769 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.7103. Min Act: -0.1700
Data Index: 8165752 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.7103. Min Act: -0.1700
Data Index: 4368490 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.6791. Min Act: -0.1700
Data Index: 404384 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.6478. Min Act: -0.1700
Data Index: 4554247 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.6478. Min Act: -0.1700
Data Index: 2690809 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.6478. Min Act: -0.1700
Data Index: 3348407 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.6166. Min Act: -0.1700
Data Index: 6236109 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.5853. Min Act: -0.1700
Data Index: 2628385 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3666. Min Range: -6.3666
Max Act: 5.5853. Min Act: -0.1700
Data Index: 1473860 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19